Linguistic Steganalysis via LLMs: Two Modes for Efficient Detection of Strongly Concealed Stego

• URL: http://arxiv.org/abs/2406.04218v2
• Date: Fri, 21 Jun 2024 05:17:53 GMT
• Title: Linguistic Steganalysis via LLMs: Two Modes for Efficient Detection of Strongly Concealed Stego
• Authors: Yifan Tang, Yihao Wang, Ru Zhang, Jianyi Liu,
• Abstract summary: We design a novel LS with two modes called LSGC. In the generation mode, we created an LS-task "description" In the classification mode, LSGC deleted the LS-task "description" and used the "causalLM" LLMs to extract steganographic features.
• Score: 6.99735992267331
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To detect stego (steganographic text) in complex scenarios, linguistic steganalysis (LS) with various motivations has been proposed and achieved excellent performance. However, with the development of generative steganography, some stegos have strong concealment, especially after the emergence of LLMs-based steganography, the existing LS has low detection or cannot detect them. We designed a novel LS with two modes called LSGC. In the generation mode, we created an LS-task "description" and used the generation ability of LLM to explain whether texts to be detected are stegos. On this basis, we rethought the principle of LS and LLMs, and proposed the classification mode. In this mode, LSGC deleted the LS-task "description" and used the "causalLM" LLMs to extract steganographic features. The LS features can be extracted by only one pass of the model, and a linear layer with initialization weights is added to obtain the classification probability. Experiments on strongly concealed stegos show that LSGC significantly improves detection and reaches SOTA performance. Additionally, LSGC in classification mode greatly reduces training time while maintaining high performance.

Related papers

• Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement Measurement [51.601916604301685]
  Large language models (LLMs) generate content that can undermine trust in online discourse. Current methods often focus on binary classification, failing to address the complexities of real-world scenarios like human-AI collaboration. To move beyond binary classification and address these challenges, we propose a new paradigm for detecting LLM-generated content.
  arXiv  Detail & Related papers  (2024-10-18T08:14:10Z)
• DALD: Improving Logits-based Detector without Logits from Black-box LLMs [56.234109491884126]
  Large Language Models (LLMs) have revolutionized text generation, producing outputs that closely mimic human writing. We present Distribution-Aligned LLMs Detection (DALD), an innovative framework that redefines the state-of-the-art performance in black-box text detection. DALD is designed to align the surrogate model's distribution with that of unknown target LLMs, ensuring enhanced detection capability and resilience against rapid model iterations.
  arXiv  Detail & Related papers  (2024-06-07T19:38:05Z)
• ReMoDetect: Reward Models Recognize Aligned LLM's Generations [55.06804460642062]
  Large language models (LLMs) generate human-preferable texts. In this paper, we identify the common characteristics shared by these models. We propose two training schemes to further improve the detection ability of the reward model.
  arXiv  Detail & Related papers  (2024-05-27T17:38:33Z)
• Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics [50.982315553104975]
  We investigate the bottom-up evolution of lexical semantics for a popular large language model, namely Llama2. Our experiments show that the representations in lower layers encode lexical semantics, while the higher layers, with weaker semantic induction, are responsible for prediction. This is in contrast to models with discriminative objectives, such as mask language modeling, where the higher layers obtain better lexical semantics.
  arXiv  Detail & Related papers  (2024-03-03T13:14:47Z)
• MultiLS: A Multi-task Lexical Simplification Framework [21.81108113189197]
  We present MultiLS, the first LS framework that allows for the creation of a multi-task LS dataset. We also present MultiLS-PT, the first dataset to be created using the MultiLS framework.
  arXiv  Detail & Related papers  (2024-02-22T21:16:18Z)
• The Lay Person's Guide to Biomedicine: Orchestrating Large Language Models [38.8292168447796]
  Large language models (LLMs) have demonstrated a remarkable capacity for text simplification, background information generation, and text evaluation. We propose a novel textitExplain-then-Summarise LS framework, which leverages LLMs to generate high-quality background knowledge. We also propose two novel LS evaluation metrics, which assess layness from multiple perspectives.
  arXiv  Detail & Related papers  (2024-02-21T03:21:14Z)
• Latent space configuration for improved generalization in supervised autoencoder neural networks [0.0]
  We propose two methods for obtaining LS with desired topology, called LS configuration. Knowing LS configuration allows to define similarity measure in LS to predict labels or estimate similarity for multiple inputs. We show that SAE trained for clothes texture classification using the proposed method generalizes well to unseen data from LIP, Market1501, and WildTrack datasets without fine-tuning.
  arXiv  Detail & Related papers  (2024-02-13T13:25:51Z)
• Label Supervised LLaMA Finetuning [13.939718306233617]
  In this paper, we introduce a label-supervised adaptation for Large Language Models (LLMs) We extract latent representations from the final LLaMA layer and project them into the label space to compute the cross-entropy loss. Remarkably, without intricate prompt engineering or external knowledge, LS-LLaMA substantially outperforms LLMs ten times its size in scale.
  arXiv  Detail & Related papers  (2023-10-02T13:53:03Z)
• LLM-Pruner: On the Structural Pruning of Large Language Models [65.02607075556742]
  Large language models (LLMs) have shown remarkable capabilities in language understanding and generation. We tackle the compression of LLMs within the bound of two constraints: being task-agnostic and minimizing the reliance on the original training dataset. Our method, named LLM-Pruner, adopts structural pruning that selectively removes non-critical coupled structures.
  arXiv  Detail & Related papers  (2023-05-19T12:10:53Z)
• Zero-Shot Cross-Lingual Summarization via Large Language Models [108.30673793281987]
  Cross-lingual summarization ( CLS) generates a summary in a different target language. Recent emergence of Large Language Models (LLMs) has attracted wide attention from the computational linguistics community. In this report, we empirically use various prompts to guide LLMs to perform zero-shot CLS from different paradigms.
  arXiv  Detail & Related papers  (2023-02-28T01:27:37Z)
• Weakly Supervised Label Smoothing [15.05158252504978]
  We study Label Smoothing (LS), a widely used regularization technique, in the context of neural learning to rank (L2R) models. Inspired by our investigation of LS in the context of neural L2R models, we propose a novel technique called Weakly Supervised Label Smoothing (WSLS)
  arXiv  Detail & Related papers  (2020-12-15T19:36:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.